Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2320 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.5077. Min Act: -0.0003

Data Index: 359730 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4942. Min Act: -0.0003

Data Index: 165871 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4706. Min Act: -0.0003

Data Index: 1078421 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4639. Min Act: -0.0003

Data Index: 777001 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4544. Min Act: -0.0002

Data Index: 582464 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4493. Min Act: -0.0003

Data Index: 669415 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4226. Min Act: -0.0003

Data Index: 1174537 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4360. Min Act: -0.0003

Data Index: 805312 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4354. Min Act: -0.0003

Data Index: 567800 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4312. Min Act: -0.0002

Data Index: 1009450 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4298. Min Act: -0.0003

Data Index: 169051 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4219. Min Act: -0.0003

Data Index: 649315 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4173. Min Act: -0.0003

Data Index: 100070 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4156. Min Act: -0.0003

Data Index: 318555 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4143. Min Act: -0.0003

Data Index: 898551 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3994. Min Act: -0.0003

Data Index: 1166376 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4129. Min Act: -0.0003

Data Index: 408497 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4096. Min Act: -0.0003

Data Index: 1081545 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4087. Min Act: -0.0003

Data Index: 77560 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3937. Min Act: -0.0002

Data Index: 715762 (C4 (Web Text))

Max Activating Token Index: 291